Industrial internet equipment data intelligent analysis processing method and system and medium

Abstract

The invention provides an intelligent analysis and processing method and system for industrial internet equipment data and a medium, and belongs to the technical field of equipment data analysis and processing.The method comprises the steps that a general data interface is defined to integrate a mainstream industrial communication protocol, and equipment data types are automatically matched based on an equipment template library and are matched with an optimal communication protocol for collection; constructing an industrial equipment knowledge graph and converting the extracted heterogeneous data into uniform features; cleaning and preprocessing the collected data to generate optimal processing parameters; analyzing the optimal processing parameters by using a meta-learning-based rapid adaptive large model, predicting the service life of the equipment, and performing equipment health assessment and equipment energy consumption analysis; and displaying the analysis result of the industrial equipment data by using a visual component. According to the invention, by integrating a general data interface, a data processing algorithm, a deep analysis model and a visual display component, efficient acquisition, accurate preprocessing, deep analysis and visual display of industrial equipment data are realized.

Description

Technical Field

[0001] The present application belongs to the technical field of equipment data analysis and processing, and specifically relates to a method, system and medium for intelligent analysis and processing of industrial Internet equipment data. Background Art

[0002] With the development of the Industrial Internet of Things (IIoT), industrial equipment data is growing exponentially, and data processing and analysis have become key links in industrial production. However, existing data processing and analysis methods have many shortcomings.

[0003] First, traditional data collection methods are limited by protocol adaptation due to differences in interface standards. This means that a single protocol's adaptability is incompatible with heterogeneous interfaces across different vendors' devices, leading to the loss of significant equipment data and making it difficult for companies to fully monitor equipment operating status. Second, traditional data processing methods struggle to accurately identify and effectively remove data noise and outliers generated under complex operating conditions, resulting in significant deviations in analytical results. For example, when analyzing equipment temperature data, the inability to effectively remove outliers reduced the accuracy of equipment failure predictions based on this data by 30%. Third, analytical results are often presented in obscure reports or unprocessed raw data, making it difficult for company managers and frontline operators to quickly identify key information. Furthermore, equipment health management lacks real-time dynamic monitoring and intelligent early warning capabilities, resulting in delayed responses to sudden equipment failures and high downtime costs. Finally, energy management is extensive, leading to widespread energy waste.

[0004] In summary, traditional data collection, analysis, processing and display methods can no longer meet the needs of industrial enterprises for intelligent and efficient production. Summary of the Invention

[0005] In a first aspect, an embodiment of the present application provides a method for intelligent analysis and processing of industrial Internet device data, comprising the following steps: S1. Define a universal data interface that integrates mainstream industrial communication protocols, automatically matches device data types based on a device template library, and adapts to the optimal communication protocol for data collection; S2. Build an industrial equipment knowledge graph, introducing industrial equipment types, failure mode association rules, and feature mapping relationships; S3. Extract common features of industrial equipment data based on the industrial equipment knowledge graph and convert heterogeneous data from different industrial equipment into a unified feature representation; S4. Use the random forest algorithm combined with the dynamic normalization algorithm to clean and denoise the collected data, and generate the optimal processing parameters through adaptive parameter optimization based on working condition perception; S5. Analyze the optimal processing parameters using a large, fast-adaptive model based on meta-learning, and combine the association rules of the knowledge graph to predict equipment lifespan, perform equipment health assessment, and analyze equipment energy consumption; S6. Use visualization components to display the analysis results of industrial equipment data.

[0006] Furthermore, the specific steps of step S1 are as follows: S11 defines the physical layer of a universal data interface, the universal data interface includes an Ethernet interface and a serial port; S12 is a universal data interface that integrates mainstream industrial communication protocols, including the OPC protocol, Modbus-TCP / RTU protocol, and Profinet protocol; S13. Build a device template library in the universal data interface to store communication configuration templates for different industrial devices. The communication configuration template has data type mapping rules, sampling parameters, and device address definitions; S14. Automatically match the data type of the target industrial equipment based on the device template library, select the optimal communication protocol from various mainstream industrial communication protocols, and use the optimal communication protocol to map the data type after collecting industrial equipment data according to the configured collection parameters.

[0007] Furthermore, the specific steps of step S2 are as follows: S21. Build an industrial equipment knowledge graph to store the equipment type topology of industrial equipment classification; S22. Define the failure modes of each equipment type in the industrial equipment knowledge graph, the mapping relationship between each failure mode and characteristic parameters, and the life attenuation coefficient corresponding to each failure mode; S23. Storing the impact weights of associated devices and the failure propagation paths between associated device types in the industrial equipment knowledge graph; S24. Store the benchmark life curve of typical equipment in the industrial equipment knowledge graph.

[0008] Furthermore, the specific steps of step S3 are as follows: S31. Define basic features that are independent of device type and build a basic feature set for industrial equipment; S32. Identify specific characteristics of each type of device; S33. Establish a feature mapping relationship library, map device-specific features to a universal feature space, and construct a specific feature set for industrial equipment; S34. Integrate the basic feature set of industrial equipment and the specific feature set of industrial equipment into a general feature set of industrial equipment.

[0009] Furthermore, the specific steps of step S4 are as follows: S41. Use a message queue to receive industrial equipment data as a data stream, use a sliding window cache, detect and remove invalid data; S42. Perform a preliminary working condition judgment on the industrial equipment data after removing invalid data; S43. Calculate the mean and standard deviation of the industrial equipment data within the sliding window under normal detection conditions, use the mean and standard deviation to set a first dynamic threshold, and start sudden anomaly detection for industrial equipment data that exceeds the dynamic threshold; S44. In the sudden anomaly detection condition, the second dynamic threshold is set using the mean and standard deviation of the industrial equipment data, and random forest anomaly detection is started for the industrial equipment data that exceeds the second dynamic threshold set number of times; S45. For equipment aging conditions, use linear regression to analyze the long-term trend of industrial equipment data and automatically adjust the threshold; S46. Recalculate the mean and standard deviation of the industrial equipment data for which the working condition judgment has been completed, and standardize according to the recalculated mean and standard deviation; S47. Normalize the standardized industrial equipment data to obtain optimal processing parameters.

[0010] Furthermore, the specific steps of step S5 are as follows: S51. Divide the optimal processing parameters of industrial equipment data into structured data and unstructured data, and obtain equipment type-related feature mapping rules from the industrial equipment knowledge graph; S52. Construct equipment analysis tasks, equipment health assessment tasks, and equipment energy consumption analysis tasks; S53. Perform equipment analysis tasks, using a meta-learning-based LSTM-Transformer hybrid model combined with an industrial equipment knowledge graph to analyze time-series structured data to predict equipment remaining life. Also, use a large AI model to extract key events from unstructured data, and generate an equipment operating status assessment report based on the predicted equipment remaining life and extracted key events. S54. Perform the equipment health assessment task, extract characteristic parameters from the structured data and score them, and perform weighted summation of various characteristic parameters to obtain the comprehensive health index of the equipment; S55. Perform equipment energy consumption analysis tasks, extract equipment energy consumption parameters from structured data, use AI large model analysis to determine high energy consumption operation stages, analyze the causes of high energy consumption, and generate energy consumption analysis reports.

[0011] Furthermore, in step S53, the specific steps of using the meta-learning-based LSTM-Transformer hybrid model combined with the industrial equipment knowledge graph to analyze the time-series structured data and predict the remaining life of the equipment are as follows: SS1. Build a meta-learning-based LSTM-Transformer hybrid model as a device life prediction model; SS2. Use the historically optimal processing parameters of industrial equipment as a training dataset to pre-train the equipment life prediction model; SS3. Determine the type of industrial equipment to be processed based on the equipment template library. Select N sets of optimal processing parameters from similar industrial equipment that are less than a set threshold as the adaptation data set input to fine-tune the pre-trained equipment life prediction model. SS4. Perform equipment analysis tasks, inputting time-series structured data into the fine-tuned equipment life prediction model for analysis, predicting the remaining life of the equipment, and using the life attenuation coefficient corresponding to the existing failure mode of the current equipment in the industrial equipment knowledge graph, the failure impact weight of the associated equipment, and the failure propagation path between the associated equipment types for correction.

[0012] Furthermore, the specific steps of step S6 are as follows: S61. Determine visualization requirements based on user roles and decision scenarios; S62. Obtain optimal processing parameters for industrial equipment data, equipment operating status assessment reports, equipment comprehensive health index, and energy consumption analysis reports as display data, and cache frequently accessed display data using Redis; S63. Select an appropriate visualization component based on the display data type and visualization requirements; S64. Build a front-end interactive interface based on the Vue framework, and display the data using selected visualization components.

[0013] In a second aspect, an embodiment of the present application further provides an industrial Internet device data intelligent analysis and processing system, comprising: The data acquisition module is used to define a universal data interface that integrates mainstream industrial communication protocols, automatically matches device data types based on the device template library, and adapts to the optimal communication protocol for data acquisition; The knowledge graph construction module is used to construct the knowledge graph of industrial equipment, introducing industrial equipment types, failure mode association rules, and feature mapping relationships; The feature unification module is used to extract common features of industrial equipment data based on the industrial equipment knowledge graph and convert heterogeneous data from different industrial equipment into a unified feature representation; The data processing module is used to clean and remove noise from the collected data using a random forest algorithm combined with a dynamic normalization algorithm, and to generate optimal processing parameters through adaptive parameter optimization based on working condition perception; A data analysis module is used to analyze the optimal processing parameters using a large, fast-adaptive model based on meta-learning, and to predict equipment lifespan, perform equipment health assessment, and analyze equipment energy consumption in combination with association rules from the knowledge graph; The data display module is used to display the analysis results of industrial equipment data using visualization components.

[0014] In a third aspect, an embodiment of the present application further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for intelligent analysis and processing of industrial Internet device data as described in the first aspect are implemented.

[0015] It can be seen from the above technical solutions that this application has the following advantages: The intelligent analysis and processing method, system and medium for industrial Internet device data provided in this application integrate mainstream industrial protocols through a universal data interface, and realize "plug and play" data collection in combination with a device template library, thereby reducing the complexity of integration; by combining the random forest algorithm with the dynamic normalization algorithm, an adaptive parameter optimization mechanism is constructed, so that the data processing model can autonomously match the equipment operating status and improve the accuracy of anomaly detection; the meta-learning-based model can quickly adapt to new equipment types through a small number of samples, realize equipment life prediction, health assessment and energy consumption analysis, and provide comprehensive equipment status information; through a role-scenario matching visualization component library, complex analysis results are converted into decision support information, forming a closed loop of "collection-processing-analysis-decision-making", effectively solving problems such as poor data collection compatibility, inaccurate preprocessing, and non-intuitive analysis results, thereby improving the intelligence level of industrial equipment management and reducing equipment operation and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 This is a flow chart of the method for intelligent analysis and processing of industrial Internet device data according to the present invention.

[0018] Figure 2 This is a flow chart of the industrial Internet equipment data intelligent analysis and processing system of the present invention. DETAILED DESCRIPTION

[0019] The specific steps of the method for intelligent analysis and processing of industrial Internet device data will be described in detail below, and various embodiments of the present disclosure will be described more fully. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather that the present disclosure should be understood to cover all adjustments, equivalents, and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0020] For example, with the rapid development of the Industrial Internet of Things, the amount of data generated by industrial equipment has increased dramatically, and data processing and analysis have become core elements of industrial production. However, existing data processing and analysis methods have obvious shortcomings: Limited data collection: Due to the single protocol adaptability of traditional collection methods, it is difficult to be compatible with different equipment interfaces, resulting in data loss, affecting the company's comprehensive control of equipment status. Inaccurate data processing: Under complex working conditions, traditional methods cannot effectively identify and eliminate data noise and outliers, resulting in deviations in analysis results, such as a decrease in the accuracy of equipment failure prediction. Obscure data presentation: Analysis results are usually presented in a difficult-to-understand form, which is not conducive to managers and operators to quickly capture key information. Delayed health management: Equipment health management lacks real-time monitoring and early warning functions, resulting in delayed fault response and increased downtime costs. Extensive energy consumption management: Energy utilization efficiency is low and waste is serious.

[0021] To sum up, traditional data processing and analysis systems can no longer meet the needs of industrial enterprises for intelligent and efficient production.

[0022] To address the above issues, this embodiment provides a method for intelligent analysis and processing of industrial Internet device data. By integrating a universal data interface, data processing algorithms, in-depth analysis models, and visual display components, it enables efficient collection, accurate preprocessing, in-depth analysis, and intuitive display of industrial equipment data.

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0024] See also Figure 1 FIG2 is a flowchart of a method for intelligent analysis and processing of industrial Internet device data in a specific embodiment, the method comprising the following steps: S1. Define a universal data interface that integrates mainstream industrial communication protocols, automatically matches device data types based on a device template library, and adapts to the optimal communication protocol for data collection; It should be noted that by defining a universal data interface and integrating multiple mainstream industrial communication protocols, it is possible to seamlessly connect industrial equipment from different manufacturers and models, improving the compatibility and coverage of data collection. By using the device template library to automatically match device data types and select the optimal communication protocol, the workload and error probability of manual configuration are reduced, the efficiency and accuracy of data collection are improved, and the automation and intelligence of the data collection process are ensured. In addition, it is possible to collect device operation data in real time, providing data support for subsequent analysis and processing, thereby promptly discovering potential problems in equipment operation and ensuring the continuity and stability of production. S2. Build an industrial equipment knowledge graph, introducing industrial equipment types, failure mode association rules, and feature mapping relationships; It should be noted that by constructing an industrial equipment knowledge graph, storing equipment types, failure mode association rules, and feature mapping relationships, the knowledge support provided for data analysis enhances the generalization capability of the life prediction model. By defining the mapping relationship between failure modes and feature parameters, as well as the failure propagation path between equipment, the model's ability to analyze the association of equipment status is enhanced, improving the accuracy of the analysis results. S3. Extract common features of industrial equipment data based on the industrial equipment knowledge graph and convert heterogeneous data from different industrial equipment into a unified feature representation; It should be noted that by converting heterogeneous data into unified features, the versatility and adaptability of the life prediction model are improved, and feature support is provided for data analysis; S4. Use the random forest algorithm combined with the dynamic normalization algorithm to clean and denoise the collected data, and generate the optimal processing parameters through adaptive parameter optimization based on working condition perception; It should be noted that the random forest algorithm can effectively identify and remove noise and outliers in the data, and normalize the data in combination with the dynamic normalization algorithm, thereby improving the quality and consistency of the data and providing a data basis for data analysis; adaptive parameter optimization can dynamically adjust the processing parameters according to the actual operating conditions of the equipment, making the data preprocessing process more in line with actual needs and enhancing the adaptability to different working conditions; automated data cleaning and standardization processing reduces manual intervention, improves the efficiency of data preprocessing, and reduces data processing deviations caused by human factors; S5. Analyze the optimal processing parameters using a large, fast-adaptive model based on meta-learning, and combine the association rules of the knowledge graph to predict equipment lifespan, perform equipment health assessment, and analyze equipment energy consumption; It should be noted that the use of a meta-learning-based model, combined with the association rules of the knowledge graph, enables in-depth analysis of equipment data, improving the accuracy and reliability of predictions. Through equipment life prediction, health assessment, and energy consumption analysis, it provides comprehensive assessment results for equipment management, helping to optimize equipment maintenance strategies, reduce energy costs, and enhance the level of intelligent equipment management. S6. Use visualization components to display the analysis results of industrial equipment data; It should be noted that by integrating multiple visualization components, complex analysis results are presented to users in the form of intuitive and easy-to-understand charts, reports and 3D models, which reduces the difficulty of data interpretation and enables all types of personnel in the enterprise to quickly understand the operating status and analysis results of the equipment; supports personalized visualization customization based on the user's role and decision-making scenario, meets the information needs of different users in different scenarios, and improves the user experience; intuitive visualization can help users quickly capture key information.

[0025] This embodiment achieves unified data collection of different types of industrial equipment by defining a universal data interface and integrating mainstream industrial communication protocols. It improves the intelligence level of data processing and analysis through knowledge graphs and meta-learning models, and can quickly adapt to new equipment types. It displays analysis results through visual components, allowing users to intuitively understand the equipment status and facilitate decision support.

[0026] Furthermore, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process in this embodiment, another method for intelligent analysis and processing of industrial Internet device data is provided, which includes the following steps: S1. Define a universal data interface that integrates mainstream industrial communication protocols, automatically matches device data types based on the device template library, and adapts to the optimal communication protocol for data collection. The specific steps of step S1 are as follows: S11 defines the physical layer of a universal data interface, the universal data interface includes an Ethernet interface and a serial port; It should be noted that universal data interfaces are not limited to Ethernet interfaces and serial ports. For example, when adding an EtherCAT device, you only need to load the EtherCAT.driver driver package. S12 is a universal data interface that integrates mainstream industrial communication protocols, including the OPC protocol, Modbus-TCP / RTU protocol, and Profinet protocol; It should be noted that mainstream industrial communication protocols are not limited to OPC, Modbus-TCP / RTU, and Profinet. New protocols are compatible to achieve unified access across manufacturers and models of equipment. S13. Build a device template library in the universal data interface to store communication configuration templates for different industrial devices. The communication configuration template has data type mapping rules, sampling parameters, and device address definitions; For example, for a certain model of motor, its communication configuration template is as follows: Data type mapping rules: temperature (°C), vibration (mm / s), current (A) Sampling parameters: polling period is 1 second, data format is floating point number Device address definition: The device IP address is 192.168.1.100 and the port number is 502; S14. Automatically match the data type of the target industrial equipment based on the device template library, select the optimal communication protocol from various mainstream industrial communication protocols, collect industrial equipment data according to the configured collection parameters, and then use the optimal communication protocol to map the data type; For example, for a certain model of motor, the data types are automatically matched to temperature, vibration, and current, the optimal communication protocol is Modbus-TCP, data is collected according to a polling cycle of 1 second, and the collected data is mapped to the corresponding temperature, vibration, and current values; S2. Build an industrial equipment knowledge graph, introduce industrial equipment types, failure mode association rules, and feature mapping relationships; the specific steps of step S2 are as follows: S21. Build an industrial equipment knowledge graph to store the equipment type topology of industrial equipment classification; Specifically, a multi-level device type topology is constructed to classify industrial equipment according to function, purpose, and physical characteristics. For example, equipment can be divided into major categories such as "rotating machinery," "stationary equipment," and "fluid equipment," and each major category can be further subdivided into specific equipment types, such as "motor," "pump," and "heat exchanger." In the knowledge graph, each device type node contains its basic attributes, such as device name, function description, common application scenarios, etc. S22. Define the failure modes of each equipment type in the industrial equipment knowledge graph, the mapping relationship between each failure mode and characteristic parameters, and the life attenuation coefficient corresponding to each failure mode; Specifically, for each device type in the knowledge graph, its possible failure modes are defined, and a mapping relationship between failure modes and characteristic parameters is established. For example, for the "motor" device type, the failure modes are defined to include "bearing failure" and "winding short circuit". Each failure mode is associated with a set of characteristic parameters, which are key indicators for detecting and diagnosing the failure mode. For example, "bearing failure" may be associated with characteristic parameters such as "vibration frequency" and "temperature change rate." Each failure mode is assigned a life attenuation coefficient, which indicates the degree of impact of the failure mode on the equipment life. For example, a bearing failure may shorten the equipment life by 30%. S23. Storing the impact weights of associated devices and the failure propagation paths between associated device types in the industrial equipment knowledge graph; Specifically, the knowledge graph records the relationships between devices and the weights of these relationships on the propagation of device failures. For example, a "pump" device may be connected to a "motor" device. If the "motor" fails, it may cause the performance of the "pump" device to degrade. Failure propagation paths between device types are defined to describe how failures propagate from one device to another. For example, a motor failure may cause a reduction in the pump's flow rate, thereby affecting the entire production process. S24. Storing a baseline life curve of typical equipment in the industrial equipment knowledge graph; Specifically, a baseline life curve is stored for each device type in the knowledge graph. This curve represents the expected life of the device under normal operating conditions. The baseline life curve can be adjusted based on historical data and industry standards. The baseline life curve can be used to evaluate the actual operating status of the device and compare it with the predicted remaining life to determine whether the device is in an aging state. S3. Extract common features of industrial equipment data based on the industrial equipment knowledge graph and convert heterogeneous data from different industrial equipment into a unified feature representation. The specific steps of step S3 are as follows: S31. Define basic features that are independent of device type and build a basic feature set for industrial equipment; Specifically, identify a set of basic characteristics that are independent of device type and can reflect common indicators of the device's operating status. For example, the basic characteristic set may include "vibration amplitude," "temperature," "current," "pressure," etc. Define a standardized calculation method for each basic characteristic to ensure that the same characteristics of different devices can be compared. S32. Identify specific characteristics of each type of device; Specifically, for each device type, identify its unique characteristic parameters; these specific characteristic parameters are determined based on the physical characteristics and operating principles of the device; for example, for "motor" equipment, specific characteristics may include "winding resistance", "insulation strength", etc. Compare device-specific features with the base feature set to ensure that the specific features complement the base feature set and provide more comprehensive device status information; S33. Establish a feature mapping relationship library, map device-specific features to a universal feature space, and construct a specific feature set for industrial equipment; Specifically, a feature mapping relationship library is constructed to map device-specific features to a universal feature space. For example, the "winding resistance" feature of a "motor" is mapped to the universal feature category of "electrical parameters." The feature mapping relationship library contains mapping rules and conversion methods to ensure that device-specific features can be converted into universal feature representations. S34. Integrate the basic feature set of industrial equipment and the specific feature set of industrial equipment into a general feature set of industrial equipment; Specifically, the basic feature set and the device-specific feature set are integrated to form a complete universal feature set. Each feature in the universal feature set has a unified format and range to facilitate subsequent data analysis. The integrated universal feature set is normalized to ensure that all feature values are in the same range, such as [0, 1]. S4. Use the random forest algorithm combined with the dynamic normalization algorithm to clean and denoise the collected data, and generate the optimal processing parameters through the adaptive parameter optimization method based on working condition perception. The specific steps of step S4 are as follows: S41. Use a message queue to receive industrial equipment data as a data stream, use a sliding window cache, detect and remove invalid data; For example, a Kafka message queue is used to receive industrial equipment data streams, and a sliding window is used to cache data to detect and remove invalid data. For example, the sliding window size is set to 10 seconds, and data within 10 seconds is cached for processing. S42. Perform a preliminary working condition judgment on the industrial equipment data after removing invalid data; S43. Calculate the mean and standard deviation of the industrial equipment data within the sliding window under normal detection conditions, use the mean and standard deviation to set a first dynamic threshold, and start sudden anomaly detection for industrial equipment data that exceeds the dynamic threshold; Specifically, under normal detection conditions, the mean and standard deviation of the industrial equipment data in the sliding window are calculated, and the mean ± 3 times the standard deviation is used as the first dynamic threshold; For example, for device temperature data, the calculated mean is 50°C and the standard deviation is 5°C. The first dynamic threshold is 35°C to 65°C. First dynamic threshold = ; Where μ is the mean and σ is the standard deviation; S44. In the sudden anomaly detection condition, the second dynamic threshold is set using the mean and standard deviation of the industrial equipment data, and random forest anomaly detection is started for the industrial equipment data that exceeds the second dynamic threshold set number of times; For example, in the case of sudden anomaly detection, the mean ± 2 times the standard deviation is used as the second dynamic threshold. For example, for device temperature data, the calculated mean is 50°C and the standard deviation is 5°C, so the second dynamic threshold is 40°C to 60°C. If the data exceeds the second dynamic threshold for three consecutive times, random forest anomaly detection is initiated. Second dynamic threshold = ; S45. For equipment aging conditions, use linear regression to analyze the long-term trend of industrial equipment data and automatically adjust the threshold; For example, a linear regression analysis is performed on the device temperature data to obtain the temperature change trend over time. If the trend slope is greater than 0.1°C / month, the device is considered to be in an aging state, and the automatic correction threshold is increased by 1°C per year. y=a+bx Where y is temperature, x is time, a is the intercept, and b is the slope; S46. Recalculate the mean and standard deviation of the industrial equipment data for which the working condition judgment has been completed, and standardize according to the recalculated mean and standard deviation; S47. Normalize the standardized industrial equipment data to obtain optimal processing parameters; Recalculate the mean and standard deviation of the industrial equipment data that has completed the working condition judgment, and standardize it based on the recalculated mean and standard deviation. For example, for the equipment temperature data, the recalculated mean is 52°C and the standard deviation is 6°C. The standardized data is: in, z is the standardized data, x is the original data, μ is the mean, σ is the standard deviation.

[0027] Then normalize the standardized data and map the data range to the [0,1] interval:

[0028] in, x norm is the normalized data, min( x ) and max( x ) are the minimum and maximum values of the data respectively; S5. Analyze the optimal processing parameters using a large, fast-adaptive model based on meta-learning, and combine the association rules of the knowledge graph to predict equipment lifespan, perform equipment health assessment, and analyze equipment energy consumption. The specific steps of step S5 are as follows: S51. Divide the optimal processing parameters of industrial equipment data into structured data and unstructured data, and obtain equipment type-related feature mapping rules from the industrial equipment knowledge graph; Specifically, the optimal processing parameters for industrial equipment data are divided into structured data and unstructured data. Structured data includes numerical data of equipment operating parameters, such as temperature and vibration amplitude; unstructured data includes text or image data such as maintenance logs and equipment drawings; Obtain feature mapping rules related to equipment types from the industrial equipment knowledge graph to guide data segmentation and processing; S52. Construct equipment analysis tasks, equipment health assessment tasks, and equipment energy consumption analysis tasks; Specifically, different analysis tasks are defined based on device type and application scenario, including device life prediction, health assessment, and energy consumption analysis. The input data and output result formats are defined for each task to ensure that the model can correctly process and output the required information. S53. Perform equipment analysis tasks, using a meta-learning-based LSTM-Transformer hybrid model combined with an industrial equipment knowledge graph to analyze time-series structured data to predict equipment remaining life. Also, use a large AI model to extract key events from unstructured data, and generate an equipment operating status assessment report based on the predicted equipment remaining life and extracted key events. The specific steps of step S53 are as follows: S531. Use a meta-learning-based LSTM-Transformer hybrid model combined with an industrial equipment knowledge graph to analyze time-series structured data and predict the remaining life of equipment. The specific steps are as follows: SS1. Build a meta-learning-based LSTM-Transformer hybrid model as a device life prediction model; It should be noted that a hybrid model architecture is designed to combine the advantages of LSTM and Transformer to process time-series structured data; the LSTM module is used to capture time series features, and the Transformer module is used to process key information in unstructured data; Specifically, the meta-learning-based LSTM-Transformer hybrid model includes a shared feature extraction module, an LSTM module, a Transformer module, and a prediction module; The shared feature extraction module includes an input layer that obtains the original feature data of industrial equipment, including structured data and unstructured data; a hidden layer that uses a multi-layer fully connected network or convolutional neural network to extract features and output a unified feature representation; and an output layer that normalizes the extracted features into a unified feature space. The LSTM module includes an input layer that acquires time-series structured data; a hidden layer that uses a bidirectional LSTM network to capture time series features and output a time series feature representation of the device's operating status; and an output layer that concatenates the time series features with the output of the shared feature extractor. Specifically, the formula of the LSTM module is as follows:

[0029] in, is the time step t Input, is the hidden state, It is the cell state; The Transformer module includes an input layer that obtains the embedded representation of unstructured data; a hidden layer that uses a multi-head self-attention mechanism to extract key information from text or images; and an output layer that fuses the extracted key information with the output of the LSTM module. Specifically, the formula of the Transformer module is as follows:

[0030] in, Q is a query parameter, K is the key parameter, V is a value parameter, d k is the characteristic dimension; The prediction module includes an input layer that obtains the fused feature representation; a hidden layer that uses a fully connected network to perform feature conversion; and an output layer that outputs the predicted value of the remaining life of the device. Specifically, the formula of the prediction module is as follows:

[0031] in, h T is the final hidden state of the LSTM module, and MLP is a multi-layer perceptron function used to output the remaining life prediction value; SS2. Use the historically optimal processing parameters of industrial equipment as a training dataset to pre-train the equipment life prediction model; It should be noted that historical data on various equipment types, including optimal processing parameters and the actual remaining life of the equipment, is collected; this data is used to pre-train the hybrid model so that the model learns common feature representations for different equipment types; Specifically, the hybrid model is pre-trained using historical data to enable the model to learn common feature representations for different device types. The optimization goal is to minimize the prediction error. For example, the following mean square error function is used as the loss function:

[0032] Among them, RUL pred is the remaining useful life predicted by the model, RUL true is the actual remaining life, N is the number of samples; Use stochastic gradient descent or Adam optimizer for parameter updates during training; SS3. Determine the type of industrial equipment to be processed based on the equipment template library. Select N sets of optimal processing parameters from similar industrial equipment that are less than a set threshold as the adaptation data set input to fine-tune the pre-trained equipment life prediction model. It should be noted that, based on the device template library, the type of the current device is determined, and a small number of optimal processing parameters are selected from the same type of devices as the adaptation data set; Fine-tune the pre-trained model using the adapted dataset so that the model can quickly adapt to the current device type; Specifically, the loss function of fine-tuning is as follows:

[0033] in, M is the number of samples in the adapted dataset, and They are j The predicted and actual remaining life of a sample; The parameter update of the fine-tuning process is performed by the following formula:

[0034] in, are the parameters of the pre-trained model, is the fine-tuned parameter, and β is the fine-tuning learning rate; SS4. Perform equipment analysis tasks, inputting time-series structured data into a fine-tuned equipment life prediction model for analysis, predicting the remaining life of the equipment and making corrections using the life attenuation coefficient corresponding to the existing failure mode of the current equipment in the industrial equipment knowledge graph, the failure impact weights of associated equipment, and the failure propagation paths between associated equipment types. It should be noted that the time-series structured data is input into the fine-tuned model, and the model outputs the predicted value of the remaining life of the equipment; Use information from the knowledge graph to modify prediction results, taking into account failure modes, impact weights of associated devices, and failure propagation paths; For example, if the equipment has a known failure mode, the model will adjust the remaining life prediction value according to the life attenuation coefficient corresponding to the failure mode; Specifically, the lifespan attenuation correction is performed using the following formula:

[0035] Where δ is the life attenuation coefficient corresponding to the failure mode; Then perform the associated device impact correction:

[0036] Where K is the number of associated devices, is the influence weight of the kth associated device, is the impact value of the kth associated device on the remaining life of the current device; S532. Use the pre-trained BERT-Base model to parse unstructured data and extract key events based on pre-defined event types; For example, the key event definition is as follows: Bearing wear, vibration, and abnormal noise Insufficient lubrication, low oil pressure and oil level alarm For example, when the keyword “abnormal vibration” appears in the maintenance log, the key event is extracted; S533. Generate a device operating status assessment report by combining the remaining life of the device predicted by the meta-learning LSTM-Transformer hybrid model and the key events extracted by the BERT-Base model. For example, the equipment operation status assessment report includes the motor's remaining life prediction result of 500 hours, the key event "abnormal vibration", and a comprehensive assessment of the motor's possible failure risk, requiring enhanced monitoring; S54. Execute the equipment health assessment task, extract characteristic parameters from the structured data and score them, and perform weighted summation of various characteristic parameters to obtain the comprehensive health index of the equipment; the specific steps of step S33 are as follows: S541. Extracting the corresponding category of equipment parameters from the structured data as characteristic parameters; illustratively, the vibration, temperature, pressure and electrical parameters of the equipment are used as characteristic parameters; S542. The characteristic parameters of the given type are scored according to the preset scoring rules; for example, the preset air compressor vibration scoring rules are as follows: when the vibration value is within the normal range, 10 points are scored; when it exceeds the normal range but is within the allowable fluctuation range, 6 points are scored; when it exceeds the allowable fluctuation range, 2 points are scored; S543. Use the hierarchical analysis method to determine the weights of various characteristic parameters; for example, determine the vibration parameter weight of 40%, the temperature parameter weight of 30%, the pressure parameter weight of 20%, and the electrical parameter weight of 10%; S544. Perform weighted summation on each characteristic parameter based on its own weight to calculate the comprehensive health index; for example, the comprehensive health index I = 0.4 × vibration score + 0.3 × temperature score + 0.2 × pressure score + 0.1 × electrical score; S55. Execute the equipment energy consumption analysis task, extract the equipment energy consumption parameters from the structured data, use the AI large model to analyze and determine the high energy consumption operation stage, analyze the reasons for high energy consumption, and generate an energy consumption analysis report; the specific steps of step S55 are as follows: S551 extracts equipment energy consumption parameters from structured data; illustratively, taking a blast furnace of a steel plant as an example, energy consumption parameters such as power and operating time are extracted from its operating data; S552. Use AI large-scale models to analyze the periodic and trend changes in equipment energy consumption parameters and determine the energy consumption characteristics of the equipment at different operating stages; S553. Locate the high energy consumption operation phase, analyze the causes of high energy consumption, and generate an energy consumption analysis report; S6. Use the visualization component to display the analysis results of the industrial equipment data; the specific steps of step S4 are as follows: S61. Determine visualization requirements based on user roles and decision scenarios; For example, in an electronics manufacturing company, managers focus on the overall equipment operating status and energy consumption trends, which require presentation through comprehensive reports and trend charts. Maintenance personnel are more concerned with the health of the equipment, which is best presented using equipment health score sheets and fault warning charts. S62. Obtain optimal processing parameters for industrial equipment data, equipment operating status assessment reports, equipment comprehensive health index, and energy consumption analysis reports as display data, and cache frequently accessed display data using Redis; For example, taking a certain patch device as an example, frequently accessed data such as device operation status assessment reports and comprehensive health indexes are stored in the Redis cache. When users request data, they can quickly obtain it from Redis, improving data access speed. S63. Select an appropriate visualization component based on the display data type and visualization requirements; For example, a line graph is selected to display the temperature trend data of the patch equipment; a ring percentage graph is selected to display the distribution of equipment failure types; S64. Build a front-end interactive interface based on the Vue framework and display the data using the selected visualization components; For example, in the equipment management system of an electronic manufacturing enterprise, a front-end interactive interface is built based on the Vue framework, and the selected visual components are integrated into the interface. Users can intuitively view the equipment operating status, health index and energy consumption through the interface, and perform interactive operations such as zooming in and out of charts and viewing detailed data.

[0037] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0038] like Figure 2 As shown, the following is an embodiment of the industrial Internet device data intelligent analysis and processing system provided by the embodiment of the present disclosure. This system and the industrial Internet device data intelligent analysis and processing method of the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the industrial Internet device data intelligent analysis and processing system, please refer to the embodiment of the above-mentioned industrial Internet device data intelligent analysis and processing method.

[0039] The system includes: The data acquisition module is used to define a universal data interface that integrates mainstream industrial communication protocols, automatically matches device data types based on the device template library, and adapts to the optimal communication protocol for data acquisition; The knowledge graph construction module is used to construct the knowledge graph of industrial equipment, introducing industrial equipment types, failure mode association rules, and feature mapping relationships; The feature unification module is used to extract common features of industrial equipment data based on the industrial equipment knowledge graph and convert heterogeneous data from different industrial equipment into a unified feature representation; The data processing module is used to clean and remove noise from the collected data using a random forest algorithm combined with a dynamic normalization algorithm, and to generate optimal processing parameters through adaptive parameter optimization based on working condition perception; A data analysis module is used to analyze the optimal processing parameters using a large, fast-adaptive model based on meta-learning, and to predict equipment lifespan, perform equipment health assessment, and analyze equipment energy consumption in combination with association rules from the knowledge graph; The data display module is used to display the analysis results of industrial equipment data using visualization components.

[0040] This embodiment can better meet the needs of industrial enterprises in equipment data management and analysis through the interactive collaboration of the data acquisition module, knowledge graph construction module, feature unification module, data processing module, data analysis module and data module.

[0041] The industrial Internet device data intelligent analysis and processing method provided in the embodiment of the present application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiment of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown, or combine certain components, or arrange components differently. In the embodiment of the present invention, the electronic device includes but is not limited to a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0042] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, a button, a camera, a display, and a SIM card interface, etc.

[0043] It is understood that the structures illustrated in the embodiments of the present application do not constitute specific limitations on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown, or combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0044] A processor may include one or more processing units, such as a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0045] The processor can be the nerve center and command center of the electronic device. The controller can generate operation control signals based on the instruction opcode and timing signal to complete the control of instruction fetching and execution.

[0046] The processor may also include a memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or is reusing. If the processor needs to use the instruction or data again, it can directly call it from the memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0047] The above-mentioned electronic equipment realizes the definition of the intelligent analysis and processing method of industrial Internet equipment data in this application, integrates mainstream industrial communication protocols with a universal data interface, automatically matches equipment data types based on the equipment template library, and adapts the optimal communication protocol for collection; constructs an industrial equipment knowledge graph, introduces industrial equipment types, fault mode association rules and feature mapping relationships; extracts common features of industrial equipment data based on the industrial equipment knowledge graph, and converts heterogeneous data of different industrial equipment into a unified feature representation; uses a random forest algorithm combined with a dynamic normalization algorithm to clean and denoise the collected data, and generates optimal processing parameters through an adaptive parameter optimization method based on working condition perception; uses a meta-learning-based fast adaptation large model to analyze the optimal processing parameters, combines the association rules of the knowledge graph to predict equipment life, perform equipment health assessment and equipment energy consumption analysis; uses a visualization component to display the analysis results of industrial equipment data, thereby achieving the beneficial effects of efficient collection, accurate preprocessing, in-depth analysis and intuitive display of industrial equipment data through the integration of universal data interfaces, data processing algorithms, deep analysis models and visualization display components.

[0048] The storage medium provided in this application stores a program product that can implement a method for intelligent analysis and processing of industrial Internet device data.

[0049] The intelligent analysis and processing method of industrial Internet equipment data includes: defining a universal data interface to integrate mainstream industrial communication protocols, automatically matching equipment data types based on the equipment template library and adapting the optimal communication protocol for collection; constructing an industrial equipment knowledge graph, introducing industrial equipment types, failure mode association rules and feature mapping relationships; extracting common features of industrial equipment data based on the industrial equipment knowledge graph, and converting heterogeneous data of different industrial equipment into a unified feature representation; using a random forest algorithm combined with a dynamic normalization algorithm to clean and denoise the collected data, and generating optimal processing parameters through adaptive parameter optimization based on working condition perception; analyzing the optimal processing parameters using a fast adaptation large model based on meta-learning, combining the association rules of the knowledge graph to predict equipment life, perform equipment health assessment and equipment energy consumption analysis; and using visualization components to display the analysis results of industrial equipment data.

[0050] In some possible embodiments, the industrial Internet device data intelligent analysis and processing method disclosed herein can be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps described in the above "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure.

[0051] The storage medium of the present disclosure can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0052] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligent analysis and processing of industrial Internet equipment data, characterized in that: The steps include: S1. Define a universal data interface that integrates mainstream industrial communication protocols, automatically matches device data types based on a device template library, and adapts to the optimal communication protocol for data collection; S2. Build an industrial equipment knowledge graph, introducing industrial equipment types, failure mode association rules, and feature mapping relationships; S3. Extract common features of industrial equipment data based on the industrial equipment knowledge graph and convert heterogeneous data from different industrial equipment into a unified feature representation; S4. Use the random forest algorithm combined with the dynamic normalization algorithm to clean and denoise the collected data, and generate the optimal processing parameters through adaptive parameter optimization based on working condition perception; S5. Analyze the optimal processing parameters using a large, fast-adaptive model based on meta-learning, and combine the association rules of the knowledge graph to predict equipment lifespan, perform equipment health assessment, and analyze equipment energy consumption; S6. Use visualization components to display the analysis results of industrial equipment data.

2. The method for intelligent analysis and processing of industrial Internet equipment data according to claim 1, characterized in that: The specific steps of step S1 are as follows: S11 defines the physical layer of a universal data interface, the universal data interface includes an Ethernet interface and a serial port; S12 is a universal data interface that integrates mainstream industrial communication protocols, including the OPC protocol, Modbus-TCP / RTU protocol, and Profinet protocol; S13. Build a device template library in the universal data interface to store communication configuration templates for different industrial devices. The communication configuration template has data type mapping rules, sampling parameters, and device address definitions; S14. Automatically match the data type of the target industrial equipment based on the device template library, select the optimal communication protocol from various mainstream industrial communication protocols, and use the optimal communication protocol to map the data type after collecting industrial equipment data according to the configured collection parameters.

3. The method for intelligent analysis and processing of industrial Internet equipment data according to claim 2, characterized in that: The specific steps of step S2 are as follows: S21. Build an industrial equipment knowledge graph to store the equipment type topology of industrial equipment classification; S22. Define the failure modes of each equipment type in the industrial equipment knowledge graph, the mapping relationship between each failure mode and characteristic parameters, and the life attenuation coefficient corresponding to each failure mode; S23. Storing the impact weights of associated devices and the failure propagation paths between associated device types in the industrial equipment knowledge graph; S24. Store the benchmark life curve of typical equipment in the industrial equipment knowledge graph.

4. The method for intelligent analysis and processing of industrial Internet equipment data according to claim 3, characterized in that: The specific steps of step S3 are as follows: S31. Define basic features that are independent of device type and build a basic feature set for industrial equipment; S32. Identify specific characteristics of each type of device; S33. Establish a feature mapping relationship library, map device-specific features to a universal feature space, and construct a specific feature set for industrial equipment; S34. Integrate the basic feature set of industrial equipment and the specific feature set of industrial equipment into a general feature set of industrial equipment.

5. The method for intelligent analysis and processing of industrial Internet equipment data according to claim 4, characterized in that: The specific steps of step S4 are as follows: S41. Use a message queue to receive industrial equipment data as a data stream, use a sliding window cache, detect and remove invalid data; S42. Perform a preliminary working condition judgment on the industrial equipment data after removing invalid data; S43. Calculate the mean and standard deviation of the industrial equipment data within the sliding window under normal detection conditions, use the mean and standard deviation to set a first dynamic threshold, and start sudden anomaly detection for industrial equipment data that exceeds the dynamic threshold; S44. In the sudden anomaly detection condition, the second dynamic threshold is set using the mean and standard deviation of the industrial equipment data, and random forest anomaly detection is started for the industrial equipment data that exceeds the second dynamic threshold set number of times; S45. For equipment aging conditions, use linear regression to analyze the long-term trend of industrial equipment data and automatically adjust the threshold; S46. Recalculate the mean and standard deviation of the industrial equipment data for which the working condition judgment has been completed, and standardize according to the recalculated mean and standard deviation; S47. Normalize the standardized industrial equipment data to obtain optimal processing parameters.

6. The method for intelligent analysis and processing of industrial Internet equipment data according to claim 5, characterized in that: The specific steps of step S5 are as follows: S51. Divide the optimal processing parameters of industrial equipment data into structured data and unstructured data, and obtain equipment type-related feature mapping rules from the industrial equipment knowledge graph; S52. Construct equipment analysis tasks, equipment health assessment tasks, and equipment energy consumption analysis tasks; S53. Perform equipment analysis tasks, using a meta-learning-based LSTM-Transformer hybrid model combined with an industrial equipment knowledge graph to analyze time-series structured data to predict equipment remaining life. Also, use a large AI model to extract key events from unstructured data, and generate an equipment operating status assessment report based on the predicted equipment remaining life and extracted key events. S54. Perform the equipment health assessment task, extract characteristic parameters from the structured data and score them, and perform weighted summation of various characteristic parameters to obtain the comprehensive health index of the equipment; S55. Perform equipment energy consumption analysis tasks, extract equipment energy consumption parameters from structured data, use AI large model analysis to determine high energy consumption operation stages, analyze the causes of high energy consumption, and generate energy consumption analysis reports.

7. The method for intelligent analysis and processing of industrial Internet equipment data according to claim 3, characterized in that: In step S53, the specific steps of using the meta-learning-based LSTM-Transformer hybrid model combined with the industrial equipment knowledge graph to analyze the time-series structured data and predict the remaining life of the equipment are as follows: SS1. Build a meta-learning-based LSTM-Transformer hybrid model as a device life prediction model; SS2. Use the historically optimal processing parameters of industrial equipment as a training dataset to pre-train the equipment life prediction model; SS3. Determine the type of industrial equipment to be processed based on the equipment template library. Select N sets of optimal processing parameters from similar industrial equipment that are less than a set threshold as the adaptation data set input to fine-tune the pre-trained equipment life prediction model. SS4. Perform equipment analysis tasks, inputting time-series structured data into the fine-tuned equipment life prediction model for analysis, predicting the remaining life of the equipment, and using the life attenuation coefficient corresponding to the existing failure mode of the current equipment in the industrial equipment knowledge graph, the failure impact weight of the associated equipment, and the failure propagation path between the associated equipment types for correction.

8. The method for intelligent analysis and processing of industrial Internet equipment data according to claim 4, characterized in that: The specific steps of step S6 are as follows: S61. Determine visualization requirements based on user roles and decision scenarios; S62. Obtain optimal processing parameters for industrial equipment data, equipment operating status assessment reports, equipment comprehensive health index, and energy consumption analysis reports as display data, and cache frequently accessed display data using Redis; S63. Select an appropriate visualization component based on the display data type and visualization requirements; S64. Build a front-end interactive interface based on the Vue framework, and display the data using selected visualization components.

9. An industrial Internet equipment data intelligent analysis and processing system, characterized in that: include: The data acquisition module is used to define a universal data interface that integrates mainstream industrial communication protocols, automatically matches device data types based on the device template library, and adapts to the optimal communication protocol for data acquisition; The knowledge graph construction module is used to construct the knowledge graph of industrial equipment, introducing industrial equipment types, failure mode association rules, and feature mapping relationships; The feature unification module is used to extract common features of industrial equipment data based on the industrial equipment knowledge graph and convert heterogeneous data from different industrial equipment into a unified feature representation; The data processing module is used to clean and remove noise from the collected data using a random forest algorithm combined with a dynamic normalization algorithm, and to generate optimal processing parameters through adaptive parameter optimization based on working condition perception; A data analysis module is used to analyze the optimal processing parameters using a large, fast-adaptive model based on meta-learning, and to predict equipment lifespan, perform equipment health assessment, and analyze equipment energy consumption in combination with association rules from the knowledge graph; The data display module is used to display the analysis results of industrial equipment data using visualization components.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligent analysis and processing of industrial Internet device data as described in any one of claims 1 to 8 are implemented.

Images